def test_overflow_gpu_new_backend():
seed = 12345
n_substreams = 7
curr_rstate = np.array([seed] * 6, dtype="int32")
rstate = [curr_rstate.copy()]
for j in range(1, n_substreams):
rstate.append(rng_mrg.ff_2p72(rstate[-1]))
rstate = np.asarray(rstate)
rstate = gpuarray_shared_constructor(rstate)
fct = functools.partial(GPUA_mrg_uniform.new,
rstate,
ndim=None,
dtype="float32")
# should raise error as the size overflows
sizes = [
(2**31, ),
(2**32, ),
(
2**15,
2**16,
),
(2, 2**15, 2**15),
]
rng_mrg_overflow(sizes, fct, mode, should_raise_error=True)
# should not raise error
sizes = [(2**5, ), (2**5, 2**5), (2**5, 2**5, 2**5)]
rng_mrg_overflow(sizes, fct, mode, should_raise_error=False)
# should support int32 sizes
sizes = [(np.int32(2**10), ),
(np.int32(2), np.int32(2**10), np.int32(2**10))]
rng_mrg_overflow(sizes, fct, mode, should_raise_error=False)
def test_consistency_GPUA_parallel():
# Verify that the random numbers generated by GPUA_mrg_uniform, in
# parallel, are the same as the reference (Java) implementation by
# L'Ecuyer et al.
seed = 12345
n_samples = 5
n_streams = 12
n_substreams = 7 # 7 samples will be drawn in parallel
samples = []
curr_rstate = np.array([seed] * 6, dtype="int32")
for i in range(n_streams):
stream_samples = []
rstate = [curr_rstate.copy()]
for j in range(1, n_substreams):
rstate.append(rng_mrg.ff_2p72(rstate[-1]))
rstate = np.asarray(rstate)
rstate = gpuarray_shared_constructor(rstate)
new_rstate, sample = GPUA_mrg_uniform.new(rstate,
ndim=None,
dtype="float32",
size=(n_substreams, ))
rstate.default_update = new_rstate
# Not really necessary, just mimicking
# rng_mrg.MRG_RandomStream' behavior
sample.rstate = rstate
sample.update = (rstate, new_rstate)
# We need the sample back in the main memory
cpu_sample = at.as_tensor_variable(sample)
f = aesara.function([], cpu_sample, mode=mode)
for k in range(n_samples):
s = f()
stream_samples.append(s)
samples.append(np.array(stream_samples).T.flatten())
# next stream
curr_rstate = rng_mrg.ff_2p134(curr_rstate)
samples = np.array(samples).flatten()
assert np.allclose(samples, java_samples)
def test_consistency_GPUA_serial():
# Verify that the random numbers generated by GPUA_mrg_uniform, serially,
# are the same as the reference (Java) implementation by L'Ecuyer et al.
seed = 12345
n_samples = 5
n_streams = 12
n_substreams = 7
samples = []
curr_rstate = np.array([seed] * 6, dtype="int32")
for i in range(n_streams):
stream_rstate = curr_rstate.copy()
for j in range(n_substreams):
substream_rstate = np.array([stream_rstate.copy()], dtype="int32")
# Transfer to device
rstate = gpuarray_shared_constructor(substream_rstate)
new_rstate, sample = GPUA_mrg_uniform.new(rstate,
ndim=None,
dtype="float32",
size=(1, ))
rstate.default_update = new_rstate
# Not really necessary, just mimicking
# rng_mrg.MRG_RandomStreams' behavior
sample.rstate = rstate
sample.update = (rstate, new_rstate)
# We need the sample back in the main memory
cpu_sample = tensor.as_tensor_variable(sample)
f = aesara.function([], cpu_sample, mode=mode)
for k in range(n_samples):
s = f()
samples.append(s)
# next substream
stream_rstate = rng_mrg.ff_2p72(stream_rstate)
# next stream
curr_rstate = rng_mrg.ff_2p134(curr_rstate)
samples = np.array(samples).flatten()
assert np.allclose(samples, java_samples)
def test_consistency_cpu_parallel():
# Verify that the random numbers generated by mrg_uniform, in parallel,
# are the same as the reference (Java) implementation by L'Ecuyer et al.
seed = 12345
n_samples = 5
n_streams = 12
n_substreams = 7 # 7 samples will be drawn in parallel
samples = []
curr_rstate = np.array([seed] * 6, dtype="int32")
for i in range(n_streams):
stream_samples = []
rstate = [curr_rstate.copy()]
for j in range(1, n_substreams):
rstate.append(rng_mrg.ff_2p72(rstate[-1]))
rstate = np.asarray(rstate)
rstate = shared(rstate)
new_rstate, sample = rng_mrg.mrg_uniform.new(rstate,
ndim=None,
dtype=config.floatX,
size=(n_substreams, ))
# Not really necessary, just mimicking
# rng_mrg.MRG_RandomStream' behavior
sample.rstate = rstate
sample.update = (rstate, new_rstate)
rstate.default_update = new_rstate
f = function([], sample)
for k in range(n_samples):
s = f()
stream_samples.append(s)
samples.append(np.array(stream_samples).T.flatten())
# next stream
curr_rstate = rng_mrg.ff_2p134(curr_rstate)
samples = np.array(samples).flatten()
assert np.allclose(samples, java_samples)
